|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* Sitemap handling functions |
|
4
|
|
|
* |
|
5
|
|
|
* @license GPL 2 (http://www.gnu.org/licenses/gpl.html) |
|
6
|
|
|
* @author Michael Hamann <[email protected]> |
|
7
|
|
|
*/ |
|
8
|
|
|
|
|
9
|
|
|
if(!defined('DOKU_INC')) die('meh.'); |
|
10
|
|
|
|
|
11
|
|
|
/** |
|
12
|
|
|
* A class for building sitemaps and pinging search engines with the sitemap URL. |
|
13
|
|
|
* |
|
14
|
|
|
* @author Michael Hamann |
|
15
|
|
|
*/ |
|
16
|
|
|
class Sitemapper { |
|
17
|
|
|
/** |
|
18
|
|
|
* Builds a Google Sitemap of all public pages known to the indexer |
|
19
|
|
|
* |
|
20
|
|
|
* The map is placed in the cache directory named sitemap.xml.gz - This |
|
21
|
|
|
* file needs to be writable! |
|
22
|
|
|
* |
|
23
|
|
|
* @author Michael Hamann |
|
24
|
|
|
* @author Andreas Gohr |
|
25
|
|
|
* @link https://www.google.com/webmasters/sitemaps/docs/en/about.html |
|
26
|
|
|
* @link http://www.sitemaps.org/ |
|
27
|
|
|
* |
|
28
|
|
|
* @return bool |
|
29
|
|
|
*/ |
|
30
|
|
|
public static function generate(){ |
|
31
|
|
|
global $conf; |
|
32
|
|
|
if($conf['sitemap'] < 1 || !is_numeric($conf['sitemap'])) return false; |
|
33
|
|
|
|
|
34
|
|
|
$sitemap = Sitemapper::getFilePath(); |
|
35
|
|
|
|
|
36
|
|
|
if(file_exists($sitemap)){ |
|
37
|
|
|
if(!is_writable($sitemap)) return false; |
|
38
|
|
|
}else{ |
|
39
|
|
|
if(!is_writable(dirname($sitemap))) return false; |
|
40
|
|
|
} |
|
41
|
|
|
|
|
42
|
|
|
if(@filesize($sitemap) && |
|
43
|
|
|
@filemtime($sitemap) > (time()-($conf['sitemap']*86400))){ // 60*60*24=86400 |
|
44
|
|
|
dbglog('Sitemapper::generate(): Sitemap up to date'); |
|
45
|
|
|
return false; |
|
46
|
|
|
} |
|
47
|
|
|
|
|
48
|
|
|
dbglog("Sitemapper::generate(): using $sitemap"); |
|
49
|
|
|
|
|
50
|
|
|
$pages = idx_get_indexer()->getPages(); |
|
51
|
|
|
dbglog('Sitemapper::generate(): creating sitemap using '.count($pages).' pages'); |
|
52
|
|
|
$items = array(); |
|
53
|
|
|
|
|
54
|
|
|
// build the sitemap items |
|
55
|
|
|
foreach($pages as $id){ |
|
56
|
|
|
//skip hidden, non existing and restricted files |
|
57
|
|
|
if(isHiddenPage($id)) continue; |
|
58
|
|
|
if(auth_aclcheck($id,'',array()) < AUTH_READ) continue; |
|
59
|
|
|
$item = SitemapItem::createFromID($id); |
|
60
|
|
|
if ($item !== null) |
|
61
|
|
|
$items[] = $item; |
|
62
|
|
|
} |
|
63
|
|
|
|
|
64
|
|
|
$eventData = array('items' => &$items, 'sitemap' => &$sitemap); |
|
65
|
|
|
$event = new Doku_Event('SITEMAP_GENERATE', $eventData); |
|
66
|
|
|
if ($event->advise_before(true)) { |
|
67
|
|
|
//save the new sitemap |
|
68
|
|
|
$event->result = io_saveFile($sitemap, Sitemapper::getXML($items)); |
|
69
|
|
|
} |
|
70
|
|
|
$event->advise_after(); |
|
71
|
|
|
|
|
72
|
|
|
return $event->result; |
|
73
|
|
|
} |
|
74
|
|
|
|
|
75
|
|
|
/** |
|
76
|
|
|
* Builds the sitemap XML string from the given array auf SitemapItems. |
|
77
|
|
|
* |
|
78
|
|
|
* @param $items array The SitemapItems that shall be included in the sitemap. |
|
79
|
|
|
* @return string The sitemap XML. |
|
80
|
|
|
* |
|
81
|
|
|
* @author Michael Hamann |
|
82
|
|
|
*/ |
|
83
|
|
|
private static function getXML($items) { |
|
84
|
|
|
ob_start(); |
|
85
|
|
|
echo '<?xml version="1.0" encoding="UTF-8"?>'.NL; |
|
86
|
|
|
echo '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">'.NL; |
|
87
|
|
|
foreach ($items as $item) { |
|
88
|
|
|
/** @var SitemapItem $item */ |
|
89
|
|
|
echo $item->toXML(); |
|
90
|
|
|
} |
|
91
|
|
|
echo '</urlset>'.NL; |
|
92
|
|
|
$result = ob_get_contents(); |
|
93
|
|
|
ob_end_clean(); |
|
94
|
|
|
return $result; |
|
95
|
|
|
} |
|
96
|
|
|
|
|
97
|
|
|
/** |
|
98
|
|
|
* Helper function for getting the path to the sitemap file. |
|
99
|
|
|
* |
|
100
|
|
|
* @return string The path to the sitemap file. |
|
101
|
|
|
* |
|
102
|
|
|
* @author Michael Hamann |
|
103
|
|
|
*/ |
|
104
|
|
|
public static function getFilePath() { |
|
105
|
|
|
global $conf; |
|
106
|
|
|
|
|
107
|
|
|
$sitemap = $conf['cachedir'].'/sitemap.xml'; |
|
108
|
|
|
if (self::sitemapIsCompressed()) { |
|
109
|
|
|
$sitemap .= '.gz'; |
|
110
|
|
|
} |
|
111
|
|
|
|
|
112
|
|
|
return $sitemap; |
|
113
|
|
|
} |
|
114
|
|
|
|
|
115
|
|
|
/** |
|
116
|
|
|
* Helper function for checking if the sitemap is compressed |
|
117
|
|
|
* |
|
118
|
|
|
* @return bool If the sitemap file is compressed |
|
119
|
|
|
*/ |
|
120
|
|
|
public static function sitemapIsCompressed() { |
|
121
|
|
|
global $conf; |
|
122
|
|
|
return $conf['compression'] === 'bz2' || $conf['compression'] === 'gz'; |
|
123
|
|
|
} |
|
124
|
|
|
|
|
125
|
|
|
/** |
|
126
|
|
|
* Pings search engines with the sitemap url. Plugins can add or remove |
|
127
|
|
|
* urls to ping using the SITEMAP_PING event. |
|
128
|
|
|
* |
|
129
|
|
|
* @author Michael Hamann |
|
130
|
|
|
* |
|
131
|
|
|
* @return bool |
|
132
|
|
|
*/ |
|
133
|
|
|
public static function pingSearchEngines() { |
|
134
|
|
|
//ping search engines... |
|
135
|
|
|
$http = new DokuHTTPClient(); |
|
136
|
|
|
$http->timeout = 8; |
|
|
|
|
|
|
137
|
|
|
|
|
138
|
|
|
$encoded_sitemap_url = urlencode(wl('', array('do' => 'sitemap'), true, '&')); |
|
139
|
|
|
$ping_urls = array( |
|
140
|
|
|
'google' => 'http://www.google.com/webmasters/sitemaps/ping?sitemap='.$encoded_sitemap_url, |
|
141
|
|
|
'microsoft' => 'http://www.bing.com/webmaster/ping.aspx?siteMap='.$encoded_sitemap_url, |
|
142
|
|
|
'yandex' => 'http://blogs.yandex.ru/pings/?status=success&url='.$encoded_sitemap_url |
|
143
|
|
|
); |
|
144
|
|
|
|
|
145
|
|
|
$data = array('ping_urls' => $ping_urls, |
|
146
|
|
|
'encoded_sitemap_url' => $encoded_sitemap_url |
|
147
|
|
|
); |
|
148
|
|
|
$event = new Doku_Event('SITEMAP_PING', $data); |
|
149
|
|
|
if ($event->advise_before(true)) { |
|
150
|
|
|
foreach ($data['ping_urls'] as $name => $url) { |
|
151
|
|
|
dbglog("Sitemapper::PingSearchEngines(): pinging $name"); |
|
152
|
|
|
$resp = $http->get($url); |
|
153
|
|
|
if($http->error) dbglog("Sitemapper:pingSearchengines(): $http->error"); |
|
|
|
|
|
|
154
|
|
|
dbglog('Sitemapper:pingSearchengines(): '.preg_replace('/[\n\r]/',' ',strip_tags($resp))); |
|
155
|
|
|
} |
|
156
|
|
|
} |
|
157
|
|
|
$event->advise_after(); |
|
158
|
|
|
|
|
159
|
|
|
return true; |
|
160
|
|
|
} |
|
161
|
|
|
} |
|
162
|
|
|
|
|
163
|
|
|
/** |
|
164
|
|
|
* An item of a sitemap. |
|
165
|
|
|
* |
|
166
|
|
|
* @author Michael Hamann |
|
167
|
|
|
*/ |
|
168
|
|
|
class SitemapItem { |
|
169
|
|
|
public $url; |
|
170
|
|
|
public $lastmod; |
|
171
|
|
|
public $changefreq; |
|
172
|
|
|
public $priority; |
|
173
|
|
|
|
|
174
|
|
|
/** |
|
175
|
|
|
* Create a new item. |
|
176
|
|
|
* |
|
177
|
|
|
* @param string $url The url of the item |
|
178
|
|
|
* @param int $lastmod Timestamp of the last modification |
|
179
|
|
|
* @param string $changefreq How frequently the item is likely to change. Valid values: always, hourly, daily, weekly, monthly, yearly, never. |
|
180
|
|
|
* @param $priority float|string The priority of the item relative to other URLs on your site. Valid values range from 0.0 to 1.0. |
|
181
|
|
|
*/ |
|
182
|
|
|
public function __construct($url, $lastmod, $changefreq = null, $priority = null) { |
|
183
|
|
|
$this->url = $url; |
|
184
|
|
|
$this->lastmod = $lastmod; |
|
185
|
|
|
$this->changefreq = $changefreq; |
|
186
|
|
|
$this->priority = $priority; |
|
187
|
|
|
} |
|
188
|
|
|
|
|
189
|
|
|
/** |
|
190
|
|
|
* Helper function for creating an item for a wikipage id. |
|
191
|
|
|
* |
|
192
|
|
|
* @param string $id A wikipage id. |
|
193
|
|
|
* @param string $changefreq How frequently the item is likely to change. Valid values: always, hourly, daily, weekly, monthly, yearly, never. |
|
194
|
|
|
* @param float|string $priority The priority of the item relative to other URLs on your site. Valid values range from 0.0 to 1.0. |
|
195
|
|
|
* @return SitemapItem The sitemap item. |
|
196
|
|
|
*/ |
|
197
|
|
|
public static function createFromID($id, $changefreq = null, $priority = null) { |
|
198
|
|
|
$id = trim($id); |
|
199
|
|
|
$date = @filemtime(wikiFN($id)); |
|
200
|
|
|
if(!$date) return null; |
|
201
|
|
|
return new SitemapItem(wl($id, '', true), $date, $changefreq, $priority); |
|
202
|
|
|
} |
|
203
|
|
|
|
|
204
|
|
|
/** |
|
205
|
|
|
* Get the XML representation of the sitemap item. |
|
206
|
|
|
* |
|
207
|
|
|
* @return string The XML representation. |
|
208
|
|
|
*/ |
|
209
|
|
|
public function toXML() { |
|
210
|
|
|
$result = ' <url>'.NL |
|
211
|
|
|
.' <loc>'.hsc($this->url).'</loc>'.NL |
|
212
|
|
|
.' <lastmod>'.date_iso8601($this->lastmod).'</lastmod>'.NL; |
|
213
|
|
|
if ($this->changefreq !== null) |
|
214
|
|
|
$result .= ' <changefreq>'.hsc($this->changefreq).'</changefreq>'.NL; |
|
215
|
|
|
if ($this->priority !== null) |
|
216
|
|
|
$result .= ' <priority>'.hsc($this->priority).'</priority>'.NL; |
|
217
|
|
|
$result .= ' </url>'.NL; |
|
218
|
|
|
return $result; |
|
219
|
|
|
} |
|
220
|
|
|
} |
|
221
|
|
|
|
This check looks for access to properties that are not accessible from the current context.
If you need to make a property accessible to another context you can either raise its visibility level or provide an accessible getter in the defining class.